OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
RAG & Knowledge Systems

Rag In Action

Rag In Action is a public code repository accompanying a DeepSeek-based course on designing, implementing, evaluating and optimizing retrieval-augmented generation systems. Its Jupyter Notebook materials divide the workflow into modules, including document loading, chunking, embeddings, vector storage, retrieval refinement, answer generation and evaluation.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Rag In Action — OpenViST project profile in RAG & Knowledge Systems.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it when you want course-linked code for learning RAG workflows component by component, or a starting point for exploring system design, evaluation and optimization.

Who it is for

  • Learners following a practical introduction to RAG system components.
  • Developers exploring how to assemble or adapt modular retrieval and generation workflows.

Documented uses

  • Study a basic RAG implementation using LangChain or LlamaIndex.
  • Explore data loading, document chunking, embedding and vector database stages.
  • Compare retrieval improvement approaches such as query expansion, indexing, reranking and filtering.
  • Examine answer generation and evaluation modules, including RAGAS and TruLens.
Before you choose

Requirements & limits

The repository is public. Its README specifies Python 3.10 or later and provides dependency files for different frameworks and hardware configurations.

  • The basic module lists both LangChain and LlamaIndex; dependency files are provided for each.
  • The README describes CPU and GPU setup paths. CPU use is recommended with at least 16 GB RAM; the GPU route lists NVIDIA hardware with at least 8 GB memory and CUDA 11.8 or newer.
  • The module set includes optional specialist dependencies; PDF processing may require additional system packages, and some modules may require model downloads or API keys.
  • The repository is code and course material, not a documented hosted deployment or API service.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Set up a CPU LangChain environment

Prepare a Python virtual environment and install the repository's LangChain CPU dependencies.

Before you start

  • Python 3.10 or later
  • The repository's LangChain CPU requirements file
  • For macOS or Windows, use the listed Mac-Win requirements file; for Ubuntu, use the Ubuntu CPU requirements file.

Steps

  1. Create a virtual environment named venv-rag-langchain.

  2. Activate it using the command appropriate to the operating system.

  3. Install the matching LangChain CPU requirements file from 91-环境-Environment.

Expected outcome

A virtual environment with the selected LangChain CPU dependencies installed.

Guide limitations

  • This setup does not run a RAG module; the README directs users to begin with 00-简单RAG-SimpleRAG.
  • Additional packages may be needed for later modules, and some may require model downloads or API keys.
Documentation 1 ↗
COMPARE OPTIONS

Compare options for Retrieval-augmented applications

These projects document a common task and share a project role. This is a source-based comparison, not an execution benchmark or a guarantee of interchangeability.

ProjectDocumented purposePlatformAccess and requirements
Rag In ActionStudy a basic RAG implementation using LangChain or LlamaIndex.CloudThe repository is public. Its README specifies Python 3.10 or later and provides dependency files for different frameworks and hardware configurations.
LangsearchCrawl website or local data for a knowledge base.CLI, Self-hosted, Server
Hybrid Search RagCombine document retrieval and language-model generation in a configurable workflow.
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
16 October 2026
Original website title
huangjia2019/rag-in-action · Official homepage title · retained in its source language
How we review sourcesSuggest a correction